Cable fault intelligent diagnosis method and device

Abstract

The invention provides a cable fault intelligent diagnosis method and device, and belongs to the technical field of cable fault localization, and the method comprises the steps: obtaining a plurality of target signals of a target cable; compensating the plurality of target signals of the target cable to obtain a signal set of the target cable; inputting the signal set of the target cable into a target fault positioning model, and determining fault positioning information of the target cable; wherein the target fault positioning model is a fault positioning model for determining the cable according to the plurality of historical signals and the fault positioning information corresponding to the plurality of historical signals. According to the cable fault intelligent diagnosis method and device provided by the invention, the efficiency and accuracy of the cable fault positioning method can be improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of cable fault location, and more specifically, to a cable fault intelligent diagnosis method and device. Background Art

[0002] The probability of insulation failure of equipment or lines in the power supply system is very high, generally accounting for more than 70% of all power supply system failures. When a grounding fault is detected in the line, it is necessary to find the faulty grounding point as soon as possible for repair or replacement. However, the cable is very long, some of which are in the form of overhead or cable trench routing, and some cables are directly buried underground. If the fault point cannot be determined, the workload is huge. The grounding fault conditions are also complex and varied. Some are metallic grounding caused by mechanical or external force damage, and there are also intermittent grounding caused by insulation aging and non-metallic grounding caused by insulation damage. Different grounding conditions are difficult to measure. Therefore, an efficient and accurate cable fault location method is needed. Summary of the invention

[0004] The purpose of the present invention is to provide a cable fault intelligent diagnosis method and device to improve the efficiency and accuracy of the cable fault location method.

[0005] A first aspect of the embodiments of the present disclosure provides a cable fault intelligent diagnosis method, comprising: Acquire multiple target signals of the target cable; Compensating a plurality of target signals of the target cable to obtain a signal set of the target cable; The signal set of the target cable is input into a target fault location model to determine the fault location information of the target cable; wherein the target fault location model is a fault location model of the cable determined according to multiple historical signals and the fault location information corresponding to the multiple historical signals.

[0006] A second aspect of the embodiments of the present disclosure provides an intelligent cable fault diagnosis device, comprising: A signal acquisition module, used for acquiring multiple target signals of a target cable; A signal compensation module, used for compensating a plurality of target signals of the target cable to obtain a signal set of the target cable; A fault location module is used to input the signal set of the target cable into a target fault location model to determine the fault location information of the target cable; wherein the target fault location model is a fault location model of the cable determined based on multiple historical signals and the fault location information corresponding to the multiple historical signals.

[0007] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the above-mentioned cable fault intelligent diagnosis method when executing the computer program.

[0008] According to a fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned cable fault intelligent diagnosis method are implemented.

[0009] The beneficial effects of the cable fault intelligent diagnosis method and device provided by the embodiments of the present disclosure are: The disclosed embodiments can realize accurate cable fault diagnosis, and can fully reflect the cable status by acquiring multiple target signals. Compensation for the target signal can eliminate interference, improve signal quality, and make subsequent analysis more accurate. The target fault location model constructed based on historical signals uses a large amount of past data experience to further enhance the accuracy of diagnosis, accurately determine the fault location, reduce misjudgment, and provide reliable guidance for maintenance. Therefore, the disclosed embodiments can improve the efficiency and accuracy of the cable fault location method. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0011] Figure 1 A schematic diagram of a flow chart of a cable fault intelligent diagnosis method provided by an embodiment of the present disclosure; Figure 2 A structural block diagram of a cable fault intelligent diagnosis device provided by an embodiment of the present disclosure; Figure 3 A schematic block diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0012] In the following description, specific details such as specific system structures and technologies are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present disclosure. However, it should be clear to those skilled in the art that the present disclosure may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obstructing the description of the present disclosure with unnecessary details.

[0013] In order to make the purpose, technical solutions and advantages of the present disclosure more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0014] Please refer to Figure 1 , Figure 1 A schematic diagram of a process flow of a cable fault intelligent diagnosis method provided by an embodiment of the present disclosure, the method comprising: S101: Acquire multiple target signals of a target cable.

[0015] In this embodiment, the target cable refers to the cable that currently needs to be diagnosed for a fault. The target signal refers to various physical quantity signals that can reflect the operating status of the cable. Multiple target signals can reflect the status of the target cable from different aspects, and may include electrical signals, temperature signals, and partial discharge signals. The electrical signal may include current signals, voltage signals, resistance signals, and capacitance signals.

[0016] The sensors are arranged at multiple positions of the target cable to obtain multiple target signals of the target cable. Subsequently, by analyzing and processing the multiple target signals, it is possible to determine whether the target cable has a fault and the type and location of the fault.

[0017] For example, during normal operation, the current should flow stably within the rated range. For example, for a cable with a rated current of 100A, if the current is detected to suddenly increase to 200A, it indicates that a short circuit fault has occurred in the cable or an additional load has been connected.

[0018] Assume that in the power supply system of a large factory, there is a critical power supply cable identified as the target cable.

[0019] Voltage sensors are installed at both ends and in the middle of the target cable. The voltage sensors can monitor the voltage changes on the target cable in real time. For example, during normal operation, the voltage sensor detects that the voltage at both ends of the cable is 380V, while the voltage at the middle is 378V. The voltage values ​​at the above different positions are the target voltage signals obtained.

[0020] Connect a current transformer to the loop of the target cable. The current transformer can convert the large current in the cable into a small current in proportion to facilitate measurement and monitoring. For example, when the equipment in the factory is operating normally, the current transformer detects that the current in the target cable is 100A. The current value of 100A is the acquired target current signal.

[0021] This embodiment uses a partial discharge detector connected to the target cable. The partial discharge detector can detect whether there is partial discharge inside the cable. If there are problems such as insulation defects in the cable, partial discharge will occur. For example, the detector detects that a weak partial discharge signal appears in the target cable at a certain moment, and the discharge amount is 5pC. The partial discharge signal is also one of the target signals obtained.

[0022] A temperature sensor is installed on the surface of the target cable. The temperature sensor can monitor the temperature change of the cable. If the cable is overloaded or has poor contact, the temperature of the cable will rise. For example, the temperature sensor detects that the surface temperature of the target cable is 40°C. This temperature value is the target temperature signal obtained.

[0023] S102: Compensating for multiple target signals of a target cable to obtain a signal set of the target cable.

[0024] In this embodiment, compensation is to adjust and correct the target signal to more accurately reflect the real state of the cable or to be more suitable for subsequent fault location analysis. For example, if the detected target signal has noise interference, the signal is compensated by filtering and other methods to remove the noise component.

[0025] The signal set of the target cable is a set of compensated target signals, including multiple processed target signals, which are used together for subsequent fault location analysis. For example, a set of voltage signals and current signals obtained after compensation constitute the signal set of the target cable.

[0026] Compensation operations are performed on multiple target signals of a target cable in a power supply system to obtain a signal set of the target cable for subsequent intelligent diagnosis of cable faults.

[0027] Assume that in a city's power supply system, an important high-voltage cable is identified as the target cable for intelligent fault diagnosis.

[0028] By installing sensors at different locations on the cable, multiple target signals of the target cable are obtained. For example, the voltage signals at three locations are 220V, 218V, and 219V, the current signals are 50A, 48A, and 52A, and the temperature signal is 30°C.

[0029] After analysis, it was found that there was a certain amount of noise interference in the voltage and current signals, which was caused by the electromagnetic field generated by other nearby electrical equipment. The temperature signal was affected by the change of ambient temperature and had a certain measurement error.

[0030] For voltage and current signals, digital filtering technology is used to remove noise interference. After filtering, the voltage signal becomes 220.5V, 218.2V, 219.4V, and the current signal becomes 49.5A, 48.2A, 51.8A.

[0031] For the temperature signal, the calibration algorithm is used to compensate for the influence of the ambient temperature. Assuming that the ambient temperature is 25°C, the temperature signal is corrected according to the calibration formula, and the corrected temperature signal is 32°C.

[0032] The compensated voltage, current and temperature signals constitute the signal set of the target cable, which can more accurately reflect the operating status of the target cable and provide a reliable data basis for subsequent intelligent fault diagnosis.

[0033] S103: Inputting the signal set of the target cable into a target fault location model to determine the fault location information of the target cable; wherein the target fault location model is a fault location model of the cable determined according to a plurality of historical signals and the fault location information corresponding to the plurality of historical signals.

[0034] In this embodiment, the target fault location model is used to determine the target cable fault location, and the model is obtained by learning and training multiple historical signals (signals of other cables detected in the past) and the fault location information corresponding to the historical signals. For example, a neural network-based fault location model can accurately determine the specific location of the cable fault based on the input signal set through training with a large amount of historical data.

[0035] The fault location information is the specific information of the target cable fault location and fault type, for example, it is determined that a short circuit fault occurs in the target cable at a distance of 100 meters from a certain reference point.

[0036] Suppose that in the power supply system of a large factory, there is a critical cable that requires intelligent fault diagnosis.

[0037] First, build the target fault location model.

[0038] Collect multiple historical signals and corresponding fault location information. For example, in the past year, the voltage, current, temperature and other signals of different cables in the factory at different time points were recorded, as well as the fault location information determined by manual inspection when these cables failed. Assume there are 100 sets of such historical data.

[0039] The above historical data is used to train a neural network model as the target fault location model. The historical signal is used as input and the corresponding fault location information is used as output. By continuously adjusting the weights and parameters of the neural network, the model can learn the relationship between the signal and the fault location.

[0040] Then, determine the signal set of the target cable.

[0041] The target cable is monitored to obtain multiple target signals, such as the current voltage of 220V, the current of 50A, the temperature of 40°C, etc. After compensation and processing, these signals constitute the signal set of the target cable.

[0042] Finally, locate the fault.

[0043] The signal set of the target cable is input into the trained target fault location model. After calculation, the model outputs the fault location information of the target cable. For example, the model determines that the target cable has an insulation damage fault 80 meters away from the distribution room.

[0044] This embodiment can quickly and accurately determine the fault location information of the target cable through the target fault location model and the signal set of the target cable, providing a basis for timely maintenance and ensuring stable operation.

[0045] It can be concluded from the above that this embodiment can realize accurate cable fault diagnosis, and by acquiring multiple target signals, it can fully reflect the cable status. Compensation for the target signal can eliminate interference, improve signal quality, and make subsequent analysis more accurate. The target fault location model constructed based on historical signals uses a large amount of past data experience to further enhance the accuracy of diagnosis, accurately determine the fault location, reduce misjudgment, and provide reliable guidance for maintenance. Therefore, this embodiment can improve the efficiency and accuracy of the cable fault location method.

[0046] In one embodiment of the present disclosure, compensating multiple target signals of a target cable to obtain a signal set of the target cable includes: If the fluctuation of the plurality of target signals is greater than or equal to a first preset value, determining a first signal set of the target cable based on a first compensation method, and the first signal set of the target cable is used as a signal set of the target cable; If the fluctuation of the plurality of target signals is less than the first preset value, a second signal set of the target cable is determined based on the second compensation method, and the second signal set of the target cable is used as the signal set of the target cable.

[0047] In this embodiment, the multiple target signals of the target cable are various signals collected from the target cable for analyzing the cable status, such as voltage, current and other signals, which may have fluctuations and interference.

[0048] Fluctuation is the amplitude of change of the target signal within a certain period of time, which can be measured by calculating statistics such as signal difference and variance.

[0049] The first preset value is a preset threshold value used to distinguish the magnitude of signal fluctuations, so as to determine which compensation method to adopt. The first preset value can be adjusted according to actual conditions.

[0050] The first compensation method is a specific compensation method used for a signal whose fluctuation is greater than or equal to a first preset value.

[0051] The first signal set is a signal set obtained by compensating a target signal with large fluctuations by using a first compensation method.

[0052] The second compensation method is a specific compensation method used for a signal whose fluctuation is less than the first preset value.

[0053] The second signal set is a signal set obtained by compensating the target signal with smaller fluctuation by using the second compensation method.

[0054] When the collected target cable signal fluctuation is greater than or equal to a first preset value, a first compensation method is used to process multiple target signals to obtain a processed first signal set, which is used as part of the target cable signal set ultimately used for fault diagnosis.

[0055] On the contrary, when the target signal fluctuation is less than the first preset value, the second compensation method is used to process multiple target signals to obtain a second signal set, which will be used as the target cable signal set for subsequent analysis. Using different compensation methods according to the degree of signal fluctuation can process signals more specifically, improve signal quality, and thus improve the accuracy of fault diagnosis.

[0056] Assume that a target cable for power transmission is monitored, and its voltage and current signals are obtained as target signals. The first preset values ​​are set to voltage fluctuation a and current fluctuation b.

[0057] Case 1: The fluctuation is greater than or equal to the first preset value.

[0058] Assume that at a certain moment, it is detected that the voltage signal fluctuates from A1 to A2 in a short period of time, and the current signal fluctuates from B1 to B2, both exceeding the first preset value. At this time, the first compensation method adopts the weighted average filtering method. For voltage signals, newer signals are given higher weights, and the voltage values ​​of multiple consecutive sampling points are weighted averaged. For example, the voltage values ​​of the last three sampling points are A3, A4, and A5, and the weights are respectively , , , the voltage value after compensation is calculated to be A. A similar method is used for the current signal to obtain the current value after compensation. After such processing, all the compensated voltage and current signals obtained constitute the first signal set, which is used as the signal set of the target cable.

[0059] Case 2: The fluctuation is less than the first preset value.

[0060] Assume that at another moment, the voltage signal fluctuates slightly around A1, and the current signal fluctuates around B1, both of which are less than the first preset value. The second compensation method can be a simple mean filter. For example, five voltage values ​​A1, A5, A6, A7, and A8 are continuously collected, and the average value A' is calculated as the compensated voltage value. The current signal is also processed in the same way to obtain the compensated current value. These compensated voltage and current signals constitute the second signal set, which is used as the signal set of the target cable at this time for subsequent fault diagnosis and analysis.

[0061] It can be concluded from the above that this embodiment compensates for signals with different fluctuation degrees respectively. For signals with large fluctuations, the first compensation method can effectively handle the interference caused by large changes, and for signals with small fluctuations, the second compensation method can be finely adjusted. The combination of the two makes the compensated signal set more accurately reflect the real state of the cable, providing a reliable basis for fault diagnosis.

[0062] In one embodiment of the present disclosure, the first fault location model includes a first compensation method, and the first compensation method is to directly compensate for multiple target signals; The second fault location model includes a second compensation method, and the second compensation method is to compensate for multiple target signals through the second fault location model.

[0063] In this embodiment, during the operation of the first fault location model, the first compensation method inside it directly acts on the acquired target signal, and does not rely on other functions of the model itself to complete the compensation, which is a relatively simple and direct compensation operation. For example, for the acquired voltage and current signals, the signals are compensated by adjusting the pre-set fixed parameters.

[0064] The second fault location model includes a second compensation method, which is to compensate multiple target signals through the second fault location model. When the second fault location model processes the target signal, the compensation process is part of the model's internal mechanism. The model will compensate the input target signal according to its own algorithm and structure, and this compensation method is closely integrated with the overall function of the model.

[0065] Assume that a fault diagnosis is performed on the power supply cable from a substation to a factory.

[0066] Example of the first compensation method: Signal compensation: Considering the cable factor, assuming that the cable has been in use for a long time, the aging of the material may cause the resistance to increase, affecting the voltage and current signals. In terms of environmental factors, low temperature may cause the cable resistance to change further. For these situations, the first compensation method directly processes the collected voltage and current signals. For example, it is known that cable aging will increase the voltage drop by a certain proportion, and a fixed compensation coefficient is set according to the age of the cable. If the voltage signal is detected to be 220V, by calculating the voltage drop caused by aging, such as 5V (calculated based on the age and material), the voltage signal is directly compensated to 225V. It is similar for the current signal. The compensation amount is calculated based on factors that may affect the current (such as the resistance change caused by local aging of the cable affects the current size). This compensation does not rely on the subsequent calculation of the fault location model, but only corrects the original signal.

[0067] Determine the compensation amount: According to the cable material parameters and service life manual, if the cable is less than 5 years old and the material is high-quality copper, in an environment with a small temperature fluctuation range (such as ±5°C) and normal humidity (such as 40%-60%), it can be considered that the signal is less affected and no compensation is required. However, if the service life exceeds 5 years, regardless of the environment, the voltage and current signals need to be compensated according to the coefficient corresponding to the degree of aging. The compensation amount changes dynamically according to the service life. The longer the service life, the greater the compensation amount.

[0068] The first compensation formula is:

[0069] in, represents the compensated signal, represents the original signal, Indicates the age of the cable. Indicates the coefficient related to the cable material and cross-sectional area. Can be multiple target signals, It can be the first signal set of the target cable, that is, signals such as voltage and current.

[0070] Example of the second compensation method: Signal compensation: Also considering the cable and environmental factors, the collected original voltage and current signals are directly input into the second fault location model. The model analyzes the cable material, service life, current ambient temperature and humidity and other information according to the preset algorithm. For example, the model stores the resistance change curves of cables of different materials at different temperatures and humidity. If the cable material in the input signal is of a specific type, the service life is 8 years, the current temperature is 5°C, and the humidity is 50%, the model automatically calculates the compensation amount based on these conditions. The model may compensate the voltage and current signals based on its built-in neural network algorithm or the calculation method based on the physical model. For example, the model determines that the cable resistance increases at the current temperature, resulting in an increase in voltage drop and a decrease in current, and automatically adjusts the voltage signal upward and the current signal upward (because the resistance increases, the voltage drop will reduce the voltage at the load end and the current will also decrease when the total voltage remains unchanged).

[0071] Determine the amount of compensation: The model determines whether compensation is needed and the amount of compensation based on various input conditions. For example, if the ambient temperature is in a certain range (such as 0-10°C) and the cable age exceeds a certain value (such as 7 years), the model calculates the voltage and current changes that need to be compensated based on the built-in temperature-resistance and age-resistance change relationships. This compensation amount changes dynamically and changes with changes in temperature, age, and other conditions.

[0072] From the above, it can be concluded that the first compensation method directly compensates the target signal, which is suitable for situations where the signal fluctuation pattern is obvious, and can be corrected quickly and accurately. The second compensation method uses model compensation, which can be dynamically adjusted according to complex signals, and has a good processing effect on signals with small fluctuations but many interferences. The combination of the two can accurately compensate for different signal characteristics and improve signal quality.

[0073] In one embodiment of the present disclosure, the cable fault intelligent diagnosis method further includes: Determine a fault location model of the cable according to the multiple historical signals and the fault location information corresponding to the multiple historical signals; The fault location model of the cable includes a first fault location model and a second fault location model.

[0074] In this embodiment, the historical signals are various signals collected from the cable in the past, and these signals contain information about the cable in different historical periods and different operating states, such as voltage, current, partial discharge and other signals at different times.

[0075] The fault location information corresponds to the historical signal and clearly indicates the location, type and other details of the cable when a fault occurred in the past.

[0076] The cable fault location model is a model built based on a neural network algorithm, which is used to determine the location and type of cable faults based on input signals.

[0077] The fault location model of the cable is determined according to the multiple historical signals and the fault location information corresponding to the multiple historical signals: By collecting a large amount of historical cable operation signals and the corresponding location information when the fault occurs, this data is used to build a model that can determine the cable fault location based on new signals. This process involves steps such as data analysis, algorithm selection, and model training. For example, using a machine learning algorithm, the model learns the relationship pattern between historical signals and fault locations.

[0078] Suppose there is a cable fault in a city power supply network that requires intelligent diagnosis: First, historical signals and fault location information are collected.

[0079] In the past few years, a large amount of data has been collected from various cable lines in the city's power supply network. These data include hourly voltage and current signals, as well as partial discharge signals detected daily as historical signals. At the same time, whenever a cable fails, maintenance personnel determine the location of the fault (such as how many meters away from a substation) and the type of fault (such as short circuit, insulation damage, etc.) through field surveys and detection. These are fault location information. For example, at a certain moment, the voltage signal of a cable fluctuated abnormally, and the partial discharge signal increased. Later, after maintenance, it was determined that the insulation layer of the cable 500 meters away from substation A was damaged, resulting in a short circuit fault. This set of data is an example of historical signals and corresponding fault location information.

[0080] Then, the fault location model of the cable is determined.

[0081] Data preprocessing: Sort and preprocess the large amount of historical signals and fault location information collected. For example, normalize the voltage and current signals so that the data range is within a certain range to facilitate subsequent model training. Encode the fault location information and convert different types of faults and location information into a format that the model can recognize.

[0082] Model selection and training: Select an appropriate machine learning algorithm to build a fault location model. Here, a neural network is used as an example. The processed historical signal is used as the input layer data, and the fault location information is used as the output layer data. The neural network is trained with a large amount of historical data, and the weights and thresholds in the network are adjusted so that the model can learn the complex relationship between historical signals and fault location.

[0083] The first fault location model is mainly used to deal with situations where the signal fluctuations are large and the changes are relatively regular. For example, in some large industrial power consumption areas, due to the frequent start and stop of equipment, the voltage and current signals on the cable will have large periodic fluctuations. When these fluctuations exceed a certain threshold, the first fault location model will be activated.

[0084] The second fault location model is suitable for situations where the signal fluctuation is small but there may be complex noise interference. For example, in some residential areas, the power supply cables have relatively stable signals but are easily affected by electromagnetic interference in the surrounding environment.

[0085] By utilizing the cable fault location model composed of the first fault location model and the second fault location model, the cable faults in the power supply system can be intelligently diagnosed more accurately.

[0086] Exemplarily, how to determine the fault location information corresponding to multiple historical signals can be done in the following manner: The signal generation circuit is based on the STM32F103 processor. The STM32F103 processor calculates the voltage value that the DC generator needs to output according to the requirements of the injection signal, and injects it into the fault line and shielding layer or (protective ground) after charging through a constant current source to reach the required voltage value. After detecting that the DC arc current is stable, a low-voltage step pulse signal is injected, and high-precision timing is turned on to detect the reflected signal. The step pulse signal is emitted at the fault point. After the traveling wave detection circuit collects the reflected signal, it stops timing and starts storage and analysis. After confirming the reflected traveling wave, the distance from the fault point to the device is calculated. Maintenance personnel can also use a handheld insulation fault detector to reconfirm the fault point.

[0087] The controller first controls the DC voltage to be added to the fault line to generate an arc at the fault point. At the same time, it uses high-speed AD and FPGA modules to detect the arc current. When it is detected that the arc current tends to be stable, it immediately injects a low-voltage step pulse signal into the line (depending on the line, the step pulse period is in milliseconds). After the low-voltage step pulse signal is injected, a reflected signal will be generated at the ground fault point (the point where the load impedance does not match the characteristic impedance), and the reflected signal will be reflected back to the sending device.

[0088] After the device detects the distance to the fault point, it can roughly determine the fault location. At this time, a fixed-frequency sinusoidal AC signal is sent out according to the cable situation. For shielded cables, the AC signal leaks at the insulation grounding fault point, generating an alternating magnetic field of the same frequency; for unshielded cables, the alternating magnetic field strengths on both sides of the insulation grounding fault point are different. The detector is a wireless signal sensing device that can detect the magnetic field strength of the sinusoidal AC signal by adjusting the resonant frequency, thereby obtaining the accurate location of the fault point. Maintenance personnel can hold the detector in the fault confirmation range for detection to further confirm the fault point.

[0089] It can be concluded from the above that this embodiment uses multiple historical signals and corresponding fault location information to build a fault location model, fully tapping the value of historical data. The first and second fault location models can process signal changes more finely for different signal conditions, reduce misdiagnosis and missed diagnosis, accurately determine the fault location, and ensure the efficiency and reliability of cable fault diagnosis.

[0090] In one embodiment of the present disclosure, the plurality of historical signals include a first historical signal set, the first historical signal set being signals whose fluctuations are greater than or equal to a first preset value; The first fault location model includes: Compensating the first historical signal set based on a first compensation method to obtain a first historical signal compensation set; A first fault location model is determined based on the first historical signal compensation set, fault location information corresponding to the first historical signal set, and a first comprehensive loss function.

[0091] In this embodiment, the first historical signal set is a part of signals screened out from a plurality of historical signals, and the fluctuation degree of these signals is greater than or equal to a preset first preset value.

[0092] The first preset value is an artificially set threshold value used to distinguish signals with different fluctuation degrees, so as to determine which historical signals belong to the first historical signal set.

[0093] The first compensation method is a method designed for the first historical signal set to correct and adjust the signal, with the purpose of reducing errors or interference factors in the signal.

[0094] The first historical signal compensation set is a new signal set obtained by processing the first historical signal set in a first compensation manner, and the signal quality in this set is relatively higher.

[0095] The first comprehensive loss function is a function used to evaluate the degree of difference between the model prediction results and the actual fault location information. It plays a key role in the process of building the first fault location model. The model is optimized by minimizing the value of this function.

[0096] This embodiment uses the compensated first historical signal compensation set and the corresponding fault location information as training data, and uses the first comprehensive loss function to measure the prediction effect of the model. By continuously adjusting the parameters of the model, the value of the first comprehensive loss function is minimized when the model processes these data, thereby determining the optimal parameters of the first fault location model and completing the construction of the model. This model can predict the fault location of the cable based on similar signal characteristics.

[0097] From the above, it can be concluded that targeted processing is performed on the first historical signal set with large fluctuations, and the compensation set is obtained through the first compensation method, which can effectively remove the abnormal fluctuation interference in the signal and make the data more real and reliable. This embodiment improves the accuracy of the model in locating cable faults under large-amplitude fluctuation signals, helps to quickly and accurately find fault points in similar fluctuation situations, reduces troubleshooting time and cost, and ensures stable operation of the power supply system.

[0098] In one embodiment of the present disclosure, the plurality of historical signals include a second historical signal set, the second historical signal set being signals whose fluctuations are less than a first preset value; The second fault location model includes: A second fault location model is determined based on the second historical signal set, the fault location information corresponding to the second historical signal set, and the second comprehensive loss function.

[0099] In this embodiment, the second historical signal set is a set of signals selected from a plurality of historical signals, and is characterized in that the signal fluctuation is less than a preset first preset value, representing a signal in a relatively stable operating state of the cable.

[0100] The second fault location model is a fault location model used to process signals with smaller fluctuations such as the second historical signal set, and its construction method is related to the characteristics of the second historical signal set.

[0101] The second comprehensive loss function is used to measure the difference between the prediction result of the second fault location model and the actual fault location information corresponding to the second historical signal set. The optimal parameters of the model are determined by optimizing the value of this function.

[0102] The second fault location model is constructed based on the second historical signal set and the corresponding fault location information. Using these data, the accuracy of the model prediction is evaluated through the second comprehensive loss function. By continuously adjusting the model parameters, the value of the second comprehensive loss function is minimized or meets certain optimization criteria, thereby determining the second fault location model that can accurately process signals with small fluctuations. This model can predict the possible fault location of the cable based on similar small fluctuation signals.

[0103] From the above, it can be concluded that this embodiment specifically constructs a second fault location model for the second historical signal set with fluctuations less than the first preset value, which can accurately capture subtle changes in the cable under relatively stable operation. In daily stable power supply scenarios, potential fault hazards can be effectively discovered to prevent small problems from accumulating into major faults.

[0104] In one embodiment of the present disclosure, the first comprehensive loss function is a weighted calculation of a mean error loss function and a distance penalty term; The second comprehensive loss function is a weighted calculation of the mean error loss function and the fault resistance estimation error term.

[0105] In this embodiment, in order to make the training of the first fault location model and the second fault location model more stable and accurate, it is necessary to perform normalization processing on the input first historical signal and the second historical signal.

[0106] The mean error loss function measures the average error between the predicted value and the true value. In the cable fault location model, the predicted value is the fault location and other information predicted by the model based on the input signal, and the true value is the actual location of the fault and other information. By calculating this average error, we can understand the overall deviation of the model prediction.

[0107] Distance penalty term (for the first comprehensive loss function): Considering that the distance between the predicted fault location and the actual fault location is a key factor in cable fault location, the distance penalty term is a quantitative penalty for the distance deviation between the predicted location and the actual location. If the predicted location is far from the actual location, the value of this term will increase, prompting the model to reduce this long-distance deviation during training.

[0108] Fault resistance estimation error term (for the second comprehensive loss function): When a cable fault occurs, the fault resistance is an important parameter. This error term is used to measure the error between the model's estimate of the fault resistance and the actual fault resistance value. For fault conditions associated with the second historical signal set with small fluctuations, accurate estimation of the fault resistance helps to locate the fault more accurately.

[0109] The expression of the first comprehensive loss function is:

[0110] in, Indicates The actual fault location information of samples, represents the first fault location model predicted The predicted fault location information of samples, represents the number of samples, express and The distance between and represents the weighting coefficient, .

[0111] The expression of the second comprehensive loss function is:

[0112] in, Indicates The actual fault location information of samples, represents the first The predicted fault location information of samples, represents the number of samples, Indicates The actual fault resistance value of the samples, represents the first The predicted fault resistance value of samples, and represents the weighting coefficient, .

[0113] From the above, it can be concluded that this embodiment can effectively avoid the large deviation of the model from the fault location and improve the positioning accuracy. Especially for signal conditions with large fluctuations, the fault point can be accurately locked and the scope of investigation can be reduced. At the same time, it helps to diagnose faults more accurately, and has more advantages in the detection and positioning of minor faults, thereby ensuring the stable operation of the cable system.

[0114] Corresponding to the intelligent cable fault diagnosis method of the above embodiment, Figure 2 This is a structural block diagram of a cable fault intelligent diagnosis device provided by an embodiment of the present disclosure. For ease of explanation, only the parts related to the embodiment of the present disclosure are shown. Figure 2 The cable fault locating device 20 includes: a signal acquisition module 21, a signal compensation module 22 and a fault locating module 23.

[0115] Wherein, the signal acquisition module 21 is used to acquire multiple target signals of the target cable; A signal compensation module 22, used for compensating a plurality of target signals of a target cable to obtain a signal set of the target cable; The fault location module 23 is used to input the signal set of the target cable into the target fault location model to determine the fault location information of the target cable; wherein the target fault location model is a fault location model of the cable determined according to multiple historical signals and the fault location information corresponding to the multiple historical signals.

[0116] In one embodiment of the present disclosure, the signal compensation module 22 is further configured to: If the fluctuation of the plurality of target signals is greater than or equal to a first preset value, determining a first signal set of the target cable based on a first compensation method, and the first signal set of the target cable is used as a signal set of the target cable; If the fluctuations of the plurality of target signals are smaller than the first preset value, a second signal set of the target cable is determined based on the second compensation method, and the second signal set of the target cable is used as the signal set of the target cable.

[0117] In one embodiment of the present disclosure, the first fault location model includes a first compensation method, and the first compensation method is to directly compensate for multiple target signals; The second fault location model includes a second compensation method, and the second compensation method is to compensate for multiple target signals through the second fault location model.

[0118] In one embodiment of the present disclosure, the intelligent cable fault diagnosis method further includes: a model building module; A model building module, used to determine a fault location model of the cable according to a plurality of historical signals and fault location information corresponding to the plurality of historical signals; The fault location model of the cable includes a first fault location model and a second fault location model.

[0119] In one embodiment of the present disclosure, the plurality of historical signals include a first historical signal set, the first historical signal set being signals whose fluctuations are greater than or equal to a first preset value; Model building modules, specifically for: Compensating the first historical signal set based on a first compensation method to obtain a first historical signal compensation set; A first fault location model is determined based on the first historical signal compensation set, fault location information corresponding to the first historical signal set, and a first comprehensive loss function.

[0120] In one embodiment of the present disclosure, the plurality of historical signals include a second historical signal set, the second historical signal set being signals whose fluctuations are less than a first preset value; Model building modules, specifically for: A second fault location model is determined based on the second historical signal set, the fault location information corresponding to the second historical signal set, and the second comprehensive loss function.

[0121] In one embodiment of the present disclosure, the first comprehensive loss function is a weighted calculation of a mean error loss function and a distance penalty term; The second comprehensive loss function is a weighted calculation of the mean error loss function and the fault resistance estimation error term.

[0122] See also Figure 3 , Figure 3 A schematic block diagram of an electronic device provided by an embodiment of the present disclosure. Figure 3The electronic device 300 in the embodiment shown may include: one or more processors 301, one or more input devices 302, one or more output devices 303 and one or more memories 304. The processors 301, input devices 302, output devices 303 and memories 304 communicate with each other via a communication bus 305. The memory 304 is used to store computer programs, which include program instructions. The processor 301 is used to execute the program instructions stored in the memory 304. The processor 301 is configured to call the program instructions to execute the functions of each module / unit in the above-mentioned device embodiments, such as Figure 2 The functions of modules 21 to 23 are shown.

[0123] It should be understood that in the embodiment of the present disclosure, the processor 301 may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0124] The input device 302 may include a touch panel, a fingerprint collection sensor (for collecting the user's fingerprint information and fingerprint direction information), a microphone, etc., and the output device 303 may include a display (LCD, etc.), a speaker, etc.

[0125] The memory 304 may include a read-only memory and a random access memory, and provide instructions and data to the processor 301. A portion of the memory 304 may also include a non-volatile random access memory. For example, the memory 304 may also store information about the device type.

[0126] In a specific implementation, the processor 301, input device 302, and output device 303 described in the embodiments of the present disclosure can execute the implementation methods described in the first and second embodiments of the intelligent diagnosis method for cable faults provided in the embodiments of the present disclosure, and can also execute the implementation methods of the electronic device described in the embodiments of the present disclosure, which will not be repeated here.

[0127] In another embodiment of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by the processor, all or part of the processes in the above-mentioned embodiment method are implemented, and the computer program can also be completed by instructing the relevant hardware through the computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor, the steps of each of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0128] The computer-readable storage medium may be an internal storage unit of the electronic device of any of the aforementioned embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Furthermore, the computer-readable storage medium may also include both an internal storage unit of the electronic device and an external storage device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.

[0129] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this disclosure.

[0130] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the electronic devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0131] In the several embodiments provided in the present application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces or units, or it can be an electrical, mechanical or other form of connection.

[0132] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present disclosure.

[0133] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0134] The above are only specific embodiments of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present disclosure, and these modifications or replacements should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A cable fault intelligent diagnosis method, characterized in that: include: Acquire multiple target signals of the target cable; Compensating a plurality of target signals of the target cable to obtain a signal set of the target cable; The signal set of the target cable is input into a target fault location model to determine the fault location information of the target cable; wherein the target fault location model is a fault location model of the cable determined according to multiple historical signals and the fault location information corresponding to the multiple historical signals.

2. The intelligent cable fault diagnosis method according to claim 1, characterized in that: The compensating the multiple target signals of the target cable to obtain the signal set of the target cable includes: If the fluctuation of the plurality of target signals is greater than or equal to a first preset value, determining a first signal set of the target cable based on a first compensation method, and using the first signal set of the target cable as the signal set of the target cable; If the fluctuations of the plurality of target signals are less than a first preset value, a second signal set of the target cable is determined based on a second compensation method, and the second signal set of the target cable is used as the signal set of the target cable.

3. The intelligent cable fault diagnosis method according to claim 2, characterized in that: The first fault location model includes the first compensation method, and the first compensation method is to directly compensate the multiple target signals; The second fault location model includes the second compensation method, and the second compensation method is to compensate the multiple target signals through the second fault location model.

4. The intelligent cable fault diagnosis method according to claim 3, characterized in that: Also includes: Determine a fault location model of the cable according to a plurality of historical signals and fault location information corresponding to the plurality of historical signals; The fault location model of the cable includes the first fault location model and the second fault location model.

5. The intelligent cable fault diagnosis method according to claim 4, characterized in that: The multiple historical signals include a first historical signal set, wherein the first historical signal set is a signal whose fluctuation is greater than or equal to a first preset value; The first fault location model includes: Compensating the first historical signal set based on the first compensation method to obtain a first historical signal compensation set; The first fault location model is determined based on the first historical signal compensation set, fault location information corresponding to the first historical signal set, and a first comprehensive loss function.

6. The intelligent cable fault diagnosis method according to claim 5, characterized in that: The plurality of historical signals include a second historical signal set, wherein the second historical signal set is a signal whose fluctuation is less than a first preset value; The second fault location model includes: The second fault location model is determined based on the second historical signal set, the fault location information corresponding to the second historical signal set, and the second comprehensive loss function.

7. The intelligent cable fault diagnosis method according to claim 6, characterized in that: The first comprehensive loss function is a weighted calculation of the average error loss function and the distance penalty term; The second comprehensive loss function is a weighted calculation of the mean value error loss function and the fault resistance estimation error term.

8. A cable fault intelligent diagnosis device, characterized in that: include: A signal acquisition module, used for acquiring multiple target signals of a target cable; A signal compensation module, used for compensating a plurality of target signals of the target cable to obtain a signal set of the target cable; A fault location module is used to input the signal set of the target cable into a target fault location model to determine the fault location information of the target cable; wherein the target fault location model is a fault location model of the cable determined based on multiple historical signals and the fault location information corresponding to the multiple historical signals.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images